* 'driver-core-next' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core-2.6: (50 commits)
printk: do not mangle valid userspace syslog prefixes
efivars: Add Documentation
efivars: Expose efivars functionality to external drivers.
efivars: Parameterize operations.
efivars: Split out variable registration
efivars: parameterize efivars
efivars: Make efivars bin_attributes dynamic
efivars: move efivars globals into struct efivars
drivers:misc: ti-st: fix debugging code
kref: Fix typo in kref documentation
UIO: add PRUSS UIO driver support
Fix spelling mistakes in Documentation/zh_CN/SubmittingPatches
firmware: Fix unaligned memory accesses in dmi-sysfs
firmware: Add documentation for /sys/firmware/dmi
firmware: Expose DMI type 15 System Event Log
firmware: Break out system_event_log in dmi-sysfs
firmware: Basic dmi-sysfs support
firmware: Add DMI entry types to the headers
Driver core: convert platform_{get,set}_drvdata to static inline functions
Translate linux-2.6/Documentation/magic-number.txt into Chinese
...
#include <asm/numa.h>
#include <asm/cacheflush.h>
#include <asm/init.h>
+ #include <asm/uv/uv.h>
static int __init parse_direct_gbpages_off(char *arg)
{
for (address = start; address <= end; address += PGDIR_SIZE) {
const pgd_t *pgd_ref = pgd_offset_k(address);
- unsigned long flags;
struct page *page;
if (pgd_none(*pgd_ref))
continue;
- spin_lock_irqsave(&pgd_lock, flags);
+ spin_lock(&pgd_lock);
list_for_each_entry(page, &pgd_list, lru) {
pgd_t *pgd;
spinlock_t *pgt_lock;
pgd = (pgd_t *)page_address(page) + pgd_index(address);
+ /* the pgt_lock only for Xen */
pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
spin_lock(pgt_lock);
spin_unlock(pgt_lock);
}
- spin_unlock_irqrestore(&pgd_lock, flags);
+ spin_unlock(&pgd_lock);
}
}
static __ref void *alloc_low_page(unsigned long *phys)
{
- unsigned long pfn = e820_table_end++;
+ unsigned long pfn = pgt_buf_end++;
void *adr;
if (after_bootmem) {
return adr;
}
- if (pfn >= e820_table_top)
+ if (pfn >= pgt_buf_top)
panic("alloc_low_page: ran out of memory");
adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
return adr;
}
+static __ref void *map_low_page(void *virt)
+{
+ void *adr;
+ unsigned long phys, left;
+
+ if (after_bootmem)
+ return virt;
+
+ phys = __pa(virt);
+ left = phys & (PAGE_SIZE - 1);
+ adr = early_memremap(phys & PAGE_MASK, PAGE_SIZE);
+ adr = (void *)(((unsigned long)adr) | left);
+
+ return adr;
+}
+
static __ref void unmap_low_page(void *adr)
{
if (after_bootmem)
return;
- early_iounmap(adr, PAGE_SIZE);
+ early_iounmap((void *)((unsigned long)adr & PAGE_MASK), PAGE_SIZE);
}
static unsigned long __meminit
return last_map_addr;
}
-static unsigned long __meminit
-phys_pte_update(pmd_t *pmd, unsigned long address, unsigned long end,
- pgprot_t prot)
-{
- pte_t *pte = (pte_t *)pmd_page_vaddr(*pmd);
-
- return phys_pte_init(pte, address, end, prot);
-}
-
static unsigned long __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
unsigned long page_size_mask, pgprot_t prot)
if (pmd_val(*pmd)) {
if (!pmd_large(*pmd)) {
spin_lock(&init_mm.page_table_lock);
- last_map_addr = phys_pte_update(pmd, address,
+ pte = map_low_page((pte_t *)pmd_page_vaddr(*pmd));
+ last_map_addr = phys_pte_init(pte, address,
end, prot);
+ unmap_low_page(pte);
spin_unlock(&init_mm.page_table_lock);
continue;
}
return last_map_addr;
}
-static unsigned long __meminit
-phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end,
- unsigned long page_size_mask, pgprot_t prot)
-{
- pmd_t *pmd = pmd_offset(pud, 0);
- unsigned long last_map_addr;
-
- last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask, prot);
- __flush_tlb_all();
- return last_map_addr;
-}
-
static unsigned long __meminit
phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
unsigned long page_size_mask)
if (pud_val(*pud)) {
if (!pud_large(*pud)) {
- last_map_addr = phys_pmd_update(pud, addr, end,
+ pmd = map_low_page(pmd_offset(pud, 0));
+ last_map_addr = phys_pmd_init(pmd, addr, end,
page_size_mask, prot);
+ unmap_low_page(pmd);
+ __flush_tlb_all();
continue;
}
/*
return last_map_addr;
}
-static unsigned long __meminit
-phys_pud_update(pgd_t *pgd, unsigned long addr, unsigned long end,
- unsigned long page_size_mask)
-{
- pud_t *pud;
-
- pud = (pud_t *)pgd_page_vaddr(*pgd);
-
- return phys_pud_init(pud, addr, end, page_size_mask);
-}
-
unsigned long __meminit
kernel_physical_mapping_init(unsigned long start,
unsigned long end,
next = end;
if (pgd_val(*pgd)) {
- last_map_addr = phys_pud_update(pgd, __pa(start),
+ pud = map_low_page((pud_t *)pgd_page_vaddr(*pgd));
+ last_map_addr = phys_pud_init(pud, __pa(start),
__pa(end), page_size_mask);
+ unmap_low_page(pud);
continue;
}
}
#ifndef CONFIG_NUMA
-void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
- int acpi, int k8)
+void __init initmem_init(void)
{
- memblock_x86_register_active_regions(0, start_pfn, end_pfn);
+ memblock_x86_register_active_regions(0, 0, max_pfn);
}
#endif
return NULL;
}
+ #ifdef CONFIG_X86_UV
+ #define MIN_MEMORY_BLOCK_SIZE (1 << SECTION_SIZE_BITS)
+
+ unsigned long memory_block_size_bytes(void)
+ {
+ if (is_uv_system()) {
+ printk(KERN_INFO "UV: memory block size 2GB\n");
+ return 2UL * 1024 * 1024 * 1024;
+ }
+ return MIN_MEMORY_BLOCK_SIZE;
+ }
+ #endif
+
#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
* Initialise the sparsemem vmemmap using huge-pages at the PMD level.
for processing it. A preliminary version of these tools is available
at <http://www.gnu.org/software/acct/>.
+config FHANDLE
+ bool "open by fhandle syscalls"
+ select EXPORTFS
+ help
+ If you say Y here, a user level program will be able to map
+ file names to handle and then later use the handle for
+ different file system operations. This is useful in implementing
+ userspace file servers, which now track files using handles instead
+ of names. The handle would remain the same even if file names
+ get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
+ syscalls.
+
config TASKSTATS
bool "Export task/process statistics through netlink (EXPERIMENTAL)"
depends on NET
select this option (if, for some reason, they need to disable it
then noswapaccount does the trick).
+config CGROUP_PERF
+ bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
+ depends on PERF_EVENTS && CGROUPS
+ help
+ This option extends the per-cpu mode to restrict monitoring to
+ threads which belong to the cgroup specified and run on the
+ designated cpu.
+
+ Say N if unsure.
+
menuconfig CGROUP_SCHED
bool "Group CPU scheduler"
depends on EXPERIMENTAL
bool
config SYSFS_DEPRECATED
- bool "enable deprecated sysfs features to support old userspace tools"
+ bool "Enable deprecated sysfs features to support old userspace tools"
depends on SYSFS
default n
help
need to say Y here.
config SYSFS_DEPRECATED_V2
- bool "enabled deprecated sysfs features by default"
+ bool "Enable deprecated sysfs features by default"
default n
depends on SYSFS
depends on SYSFS_DEPRECATED
int dmesg_restrict;
#endif
+static int syslog_action_restricted(int type)
+{
+ if (dmesg_restrict)
+ return 1;
+ /* Unless restricted, we allow "read all" and "get buffer size" for everybody */
+ return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER;
+}
+
+static int check_syslog_permissions(int type, bool from_file)
+{
+ /*
+ * If this is from /proc/kmsg and we've already opened it, then we've
+ * already done the capabilities checks at open time.
+ */
+ if (from_file && type != SYSLOG_ACTION_OPEN)
+ return 0;
+
+ if (syslog_action_restricted(type)) {
+ if (capable(CAP_SYSLOG))
+ return 0;
+ /* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */
+ if (capable(CAP_SYS_ADMIN)) {
+ WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN "
+ "but no CAP_SYSLOG (deprecated).\n");
+ return 0;
+ }
+ return -EPERM;
+ }
+ return 0;
+}
+
int do_syslog(int type, char __user *buf, int len, bool from_file)
{
unsigned i, j, limit, count;
int do_clear = 0;
char c;
- int error = 0;
+ int error;
- /*
- * If this is from /proc/kmsg we only do the capabilities checks
- * at open time.
- */
- if (type == SYSLOG_ACTION_OPEN || !from_file) {
- if (dmesg_restrict && !capable(CAP_SYSLOG))
- goto warn; /* switch to return -EPERM after 2.6.39 */
- if ((type != SYSLOG_ACTION_READ_ALL &&
- type != SYSLOG_ACTION_SIZE_BUFFER) &&
- !capable(CAP_SYSLOG))
- goto warn; /* switch to return -EPERM after 2.6.39 */
- }
+ error = check_syslog_permissions(type, from_file);
+ if (error)
+ goto out;
error = security_syslog(type);
if (error)
}
out:
return error;
-warn:
- /* remove after 2.6.39 */
- if (capable(CAP_SYS_ADMIN))
- WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN "
- "but no CAP_SYSLOG (deprecated and denied).\n");
- return -EPERM;
}
SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
}
}
+ /*
+ * Parse the syslog header <[0-9]*>. The decimal value represents 32bit, the
+ * lower 3 bit are the log level, the rest are the log facility. In case
+ * userspace passes usual userspace syslog messages to /dev/kmsg or
+ * /dev/ttyprintk, the log prefix might contain the facility. Printk needs
+ * to extract the correct log level for in-kernel processing, and not mangle
+ * the original value.
+ *
+ * If a prefix is found, the length of the prefix is returned. If 'level' is
+ * passed, it will be filled in with the log level without a possible facility
+ * value. If 'special' is passed, the special printk prefix chars are accepted
+ * and returned. If no valid header is found, 0 is returned and the passed
+ * variables are not touched.
+ */
+ static size_t log_prefix(const char *p, unsigned int *level, char *special)
+ {
+ unsigned int lev = 0;
+ char sp = '\0';
+ size_t len;
+
+ if (p[0] != '<' || !p[1])
+ return 0;
+ if (p[2] == '>') {
+ /* usual single digit level number or special char */
+ switch (p[1]) {
+ case '0' ... '7':
+ lev = p[1] - '0';
+ break;
+ case 'c': /* KERN_CONT */
+ case 'd': /* KERN_DEFAULT */
+ sp = p[1];
+ break;
+ default:
+ return 0;
+ }
+ len = 3;
+ } else {
+ /* multi digit including the level and facility number */
+ char *endp = NULL;
+
+ if (p[1] < '0' && p[1] > '9')
+ return 0;
+
+ lev = (simple_strtoul(&p[1], &endp, 10) & 7);
+ if (endp == NULL || endp[0] != '>')
+ return 0;
+ len = (endp + 1) - p;
+ }
+
+ /* do not accept special char if not asked for */
+ if (sp && !special)
+ return 0;
+
+ if (special) {
+ *special = sp;
+ /* return special char, do not touch level */
+ if (sp)
+ return len;
+ }
+
+ if (level)
+ *level = lev;
+ return len;
+ }
+
/*
* Call the console drivers, asking them to write out
* log_buf[start] to log_buf[end - 1].
cur_index = start;
start_print = start;
while (cur_index != end) {
- if (msg_level < 0 && ((end - cur_index) > 2) &&
- LOG_BUF(cur_index + 0) == '<' &&
- LOG_BUF(cur_index + 1) >= '0' &&
- LOG_BUF(cur_index + 1) <= '7' &&
- LOG_BUF(cur_index + 2) == '>') {
- msg_level = LOG_BUF(cur_index + 1) - '0';
- cur_index += 3;
+ if (msg_level < 0 && ((end - cur_index) > 2)) {
+ /* strip log prefix */
+ cur_index += log_prefix(&LOG_BUF(cur_index), &msg_level, NULL);
start_print = cur_index;
}
while (cur_index != end) {
unsigned long flags;
int this_cpu;
char *p;
+ size_t plen;
+ char special;
boot_delay_msec();
printk_delay();
printed_len += vscnprintf(printk_buf + printed_len,
sizeof(printk_buf) - printed_len, fmt, args);
-
p = printk_buf;
- /* Do we have a loglevel in the string? */
- if (p[0] == '<') {
- unsigned char c = p[1];
- if (c && p[2] == '>') {
- switch (c) {
- case '0' ... '7': /* loglevel */
- current_log_level = c - '0';
- /* Fallthrough - make sure we're on a new line */
- case 'd': /* KERN_DEFAULT */
- if (!new_text_line) {
- emit_log_char('\n');
- new_text_line = 1;
- }
- /* Fallthrough - skip the loglevel */
- case 'c': /* KERN_CONT */
- p += 3;
- break;
+ /* Read log level and handle special printk prefix */
+ plen = log_prefix(p, ¤t_log_level, &special);
+ if (plen) {
+ p += plen;
+
+ switch (special) {
+ case 'c': /* Strip <c> KERN_CONT, continue line */
+ plen = 0;
+ break;
+ case 'd': /* Strip <d> KERN_DEFAULT, start new line */
+ plen = 0;
+ default:
+ if (!new_text_line) {
+ emit_log_char('\n');
+ new_text_line = 1;
}
}
}
/*
- * Copy the output into log_buf. If the caller didn't provide
- * appropriate log level tags, we insert them here
+ * Copy the output into log_buf. If the caller didn't provide
+ * the appropriate log prefix, we insert them here
*/
- for ( ; *p; p++) {
+ for (; *p; p++) {
if (new_text_line) {
- /* Always output the token */
- emit_log_char('<');
- emit_log_char(current_log_level + '0');
- emit_log_char('>');
- printed_len += 3;
new_text_line = 0;
+ if (plen) {
+ /* Copy original log prefix */
+ int i;
+
+ for (i = 0; i < plen; i++)
+ emit_log_char(printk_buf[i]);
+ printed_len += plen;
+ } else {
+ /* Add log prefix */
+ emit_log_char('<');
+ emit_log_char(current_log_level + '0');
+ emit_log_char('>');
+ printed_len += 3;
+ }
+
if (printk_time) {
- /* Follow the token with the time */
+ /* Add the current time stamp */
char tbuf[50], *tp;
unsigned tlen;
unsigned long long t;